You can control how Adobe websites use cookies and similar technologies by making choices below. But note that if you disable cookies and similar technologies entirely, Adobe websites may not function properly.
Cookies are small text files stored by your web browser when you use websites. There are also other technologies that can be used for similar purposes like HTML5 Local Storage and local shared objects, web beacons, and embedded scripts. These technologies help us do things like remembering you and your preferences when you return to our sites, measure how you use the website, conduct market research, and gather information about the ads you see and interact with.
You can make choices in the menu below about what cookies and other technologies you want us to use on Adobe sites when you visit them from this browser. You can always change those choices later by clicking on the Cookie Preferences link at the bottom of the page.
If enabled:
We can improve your experience by tailoring the site and the content to things we think might be of interest
We can better keep track of your preferences — like what language you prefer to use
We will better understand your likely interests so we can provide you more relevant Adobe ads and content on non-Adobe websites and in non-Adobe apps
It will help us improve the performance of our website and those of our partners who use the Adobe Experience Cloud
If disabled:
We won’t be able to remember you from session to session so the experience may not be tailored to your interests
You’ll still have access to the content of the site but certain features that depend on cookies may not function
You’ll still see ads, they just may not be as relevant to you
Operate the site and core services
Always active
These cookies are required, and they are used to enable the site and related services core functionality. Without them the site could not operate, so they cannot be disabled.
Measure performance
These cookies are used to analyze site usage to measure and improve performance. Without them Adobe cannot know what content is most valued and how often unique visitors return to the site, making it hard to improve information we offer to you.
Extend functionality
These cookies are used to enhance the functionality of Adobe sites such as remembering your settings and preferences to deliver a personalized experience; for example, your username, your repeated visits, preferred language, your country, or any other saved preference.
Personalize advertising
These cookies are used to enable Adobe and our partners to serve ads more relevant to your interests. Without them you will still see ads, but they might not be as relevant to you.
Performance Cookies
ConsentLeg.Interest
All Consent Allowed
Your download's being scanned. We'll let you know if there's an issue.
Download
File format
Download
Share a link for easy access
Enable anyone to view or comment on your project with no login necessary.
Get link
PNG (Best for images)
JPG (Best for small file sizes)
PDF (Best for documents)
Add your
new text
Add your
new text
Perform aspect-based sentiment analysis on Platform X data related to airline experiences to gain a deeper understanding of customer sentiment.
Evaluate the performance of various machine learning classifiers, including Multinomial Naive Bayes, Multi-Layer Perceptron, XGBoost, Random Forest, and Support Vector Machine (SVM), for sentiment analysis.
Identify top aspects driving positive and negative sentiments towards airlines based on Platform X data.
Provide actionable insights for airlines to improve customer satisfaction and service quality based on sentiment analysis findings.
new text
Data collection involved acquiring a dataset from Kaggle, specifically the "Twitter US Airline Sentiment" dataset, comprising tweets concerning airline customer experiences. Preprocessing steps included the application of regular expressions to eliminate stopwords, URLs, and special characters, followed by the transformation of text data into a bag of words representation. Feature extraction utilized a bag of words approach to convert text data into a numerical format suitable for machine learning algorithms.
Multiple classifiers were employed for sentiment analysis, including Multinomial Naive Bayes, Multi-Layer Perceptron, XGBoost, Random Forest, and Support Vector Machine (SVM). Subsequently, the data was split into training and test sets for classifier training and evaluation, respectively. Classifiers were assessed using various metrics such as accuracy, precision, recall, and F1 score. Performance comparison revealed SVM as the top performer, demonstrating superior accuracy, precision, recall, and F1 score compared to other classifiers.
Aspect-Oriented Sentiment Analysis For Airlines
- LAKSHMI PRIYA IRAVA, MARIO M.KUBEK
Aspect-Oriented Sentiment Analysis For Airlines
- LAKSHMI PRIYA IRAVA, MARIO M.KUBEK
1. M. Taboada, J. Brooke, M. Tofiloski, K. Voll, and M.Stede. 2011. Lexicon-Based Methods for Sentiment Analysis.
2. A. Pak and P. Paroubek. 2010. Twitter as a Corpus for Sentiment Analysis and Opinion Mining.
3. A. Bermingham and A. Smeaton. 2012. On using Twitter to monitor political sentiment and predict election results.
4. M. J. Bing Liu. 2012. Sentiment Analysis and Opinion Mining.
5. S. Kiritchenko and S. Mohammad. 2018. Examining the use of machine learning techniques for sentiment analysis.
SVM achieved superior performance, excelling in detecting nuances like sarcasm and irony in X platform's airline-related data, with notable metrics including 78% accuracy, 77% precision, 78% recall, and an F1 score of 77%. This sentiment analysis provides insights for enhancing customer satisfaction and highlights the necessity for NLP advancements to overcome challenges in interpreting subtleties like sarcasm and irony.
The study demonstrates the effectiveness of machine learning classifiers for aspect-based sentiment analysis on airline-related Platform X data. By connecting sentiments to specific features of airline services, the findings provide actionable insights for targeted improvements in service areas based on sentiment analysis results.